aeo-audit
Pass
Audited by Gen Agent Trust Hub on Mar 6, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [NO_CODE]: The skill consists entirely of Markdown-based instructions for the agent and does not include any scripts, executables, or code-based dependencies.
- [DATA_EXPOSURE]: The skill instructions direct the agent to read files from the user's home directory (
~/.claude-marketing/). While this involves accessing local configuration files (profiles, guidelines, and SOPs), the access is localized to the application's own data directory and is used to provide context for the brand audit. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest brand and competitor data to perform analysis. Although the markdown instructions do not explicitly define boundary markers for untrusted content, the surface area for injection is limited to the data processed for the audit, and no specific malicious exploitation patterns are present.
Audit Metadata